|
|
Biophysics 2021
基于双边滤波与受限玻尔兹曼机的冷冻电镜单颗粒图像识别
|
Abstract:
冷冻电镜技术(Cryo-EM)起源于20世纪70年代，是结构生物学中蛋白质与核酸分子结构研究的重要技术手段。21世纪以来，计算机性能的提升与直接电子检测相机的极大发展，使得人们在小样本低剂量样本条件下仍可获得接近原子分辨率级的三维结构模型。由于三维结构模型是利用多角度投影，通过大量二维冷冻电镜单颗粒图像重构所得，因此，二维单颗粒图像的识别与分类直接影响最终模型的分辨率。目前，通过冷冻电镜获得的图像大部分噪声较多，因此对二维单颗粒图像的筛选，往往需要耗费有经验的科学工作者耗费大量时间。针对此问题，本文运用计算机图形学与机器学习相结合的方法，在预处理阶段以双边滤波器(Bilateral Filter)对信噪比较低的图像进行边缘优化，并通过直方图均衡化实现图像信息增强，最后以少量高置信度图像为训练样本，通过受限玻尔兹曼机(Restricted Boltzmann Machine，RBM)进行监督式学习并实现图像的分类与筛选，以提高二维单颗粒图像识别的效率与准确率。在方法检验阶段，首先，我们利用蛋白质数据库(Protein Data Bank, PDB)中已知的生物大分子结构，投影生成不同信噪比的模拟单颗粒模拟数据，验证了在低信噪比条件下应用本方法进行单颗粒图像识别分类的准确性。随后我们以瞬态受体电位离子通道蛋白子类V成员1 (Transient Receptor Potential cation channel subfamily V member 1，TRPV1)的真实二维单颗粒图像数据集进行识别分类与三维模型重构，通过cryoSPARC平台，以约53%的原始数据量重构出了与原分辨率3.6？相近的模型。因此，本研究不仅提高了传统人工筛选的效率，也为冷冻电镜单颗粒二维图像识别提供了新思路。
Cryo-EM is a crucial technological means to study protein and nucleic acid of structural biology which is originated in 1970s. The significant evolution of computing performance and direct electronic detection (DDD) camera make the atomic resolution of 3D structure of micromolecular under the condition of small dose possible since 21st century. The reconstruction of 3D model is based on identification and classification of 2D Cryo-EM single particle projection images which becomes an immediate cause of how good the resolution of final 3D model could share. Currently, the 2D single particle images selection was is such a time-consuming job even for the experienced scientific researchers as the signal noise ratio (SNR) is usually quite low. A new approach with the combination of computer graphics and machine learning is raised to this problem by using bilateral filter to optimize the detail of edge and histogram equalization to enhance graphic information in the pre-processing stage, moreover, small amount of high-confidence images was chosen as training sample under the restricted Boltzmann machine (RBM) network in supervised learning pattern to achieve the image selection and classification. In the verification stage, the effectiveness of this approach is proved to work well with simulated low SNR projection photos generated from the known micromolecular data from protein data bank (PDB). Subsequently, actual experimental 2D singlet particle data of transient receptor potential cation channel subfamily V member 1 (TRPV1) is applied to be identified and classified, and finally, a 3.6？ 3D structural model is reconstructed through cryoSPARC platform by using only approximate 53% of the original data. Consequently, this research is not only improving the manual efficiency, but also providing a broader
| [1] | Cheng, Y. (2018) Single-Particle Cryo-EM—How Did It Get Here and Where Will It Go. Science, 361, 876-880.
https://doi.org/10.1126/science.aat4346 |
| [2] | Cheng, Y., Grigorieff, N., Penczek, P.A. and Walz, T. (2015) A Primer to Single-Particle Cryo-Electron Microscopy. Cell, 161, 438-449. https://doi.org/10.1016/j.cell.2015.03.050 |
| [3] | Egelman, E.H. (2016) The Current Revolution in Cryo-EM. Biophysical Journal, 110, 1008-1012.
https://doi.org/10.1016/j.bpj.2016.02.001 |
| [4] | Liao, M., Cao, E., Julius, D. and Cheng, Y. (2013) Structure of the TRPV1 Ion Channel Determined by Electron Cryo-Microscopy. Nature, 504, 107-112. https://doi.org/10.1038/nature12822 |
| [5] | Huai, C., Li, G., Yao, R., Zhang, Y., Cao, M., Kong, L., Jia, C., Yuan, H., Chen, H. and Lu, D. (2017) Structural Insights into DNA Cleavage Activation of CRISPR-Cas9 System. Nature Communications, 8, 1375.
https://doi.org/10.1038/s41467-017-01496-2 |
| [6] | Bai, R., Yan, C., Wan, R., Lei, J. and Shi, Y. (2017) Structure of the Post-Catalytic Spliceosome from Saccharomyces cerevisiae. Cell, 171, 1589-1598. https://doi.org/10.1016/j.cell.2017.10.038 |
| [7] | Frank, J., Radermacher, M., Penczek, P., Zhu, J., Li, Y., Ladjadj, M. and Leith, A. (1996) SPIDER and WEB: Processing and Visualization of Images in 3D Electron Microscopy and Related Fields. Journal of Structural Biology, 116, 190-199. https://doi.org/10.1006/jsbi.1996.0030 |
| [8] | Marabini, R., Masegosa, I., San Mart？n, M., Marco, S., Fernandez, J., De La Fraga, L., Vaquerizo, C. and Carazo, J. (1996) Xmipp: An Image Processing Package for Electron Microscopy. Journal of Structural Biology, 116, 237-240.
https://doi.org/10.1006/jsbi.1996.0036 |
| [9] | Ludtke, S.J., Baldwin, P.R. and Chiu, W. (1999) EMAN: Semiautomated Software for High-Resolution Single-Particle Reconstructions. Journal of Structural Biology, 128, 82-97. https://doi.org/10.1006/jsbi.1999.4174 |
| [10] | Voss, N., Yoshioka, C., Radermacher, M., Potter, C. and Carragher, B. (2009) DoG Picker and TiltPicker: Software Tools to Facilitate Particle Selection in Single Particle Electron Microscopy. Journal of Structural Biology, 166, 205-213. https://doi.org/10.1016/j.jsb.2009.01.004 |
| [11] | Scheres, S.H. (2012) RELION: Implementation of a Bayesian Approach to Cryo-EM Structure Determination. Journal of Structural Biology, 180, 519-530. https://doi.org/10.1016/j.jsb.2012.09.006 |
| [12] | Zhang, J., Wang, Z., Chen, Y., Han, R., Liu, Z. and Sun, F. (2019) PIXER: An Automated Particle-Selection Method Based on Segmentation Using a Deep Neural Network. BMC Bioinformatics, 20, Article No. 41.
https://doi.org/10.1186/s12859-019-2614-y |
| [13] | Yao, R., Qian, J. and Huang, Q. (2019) Deep-Learning with Synthetic Data Enables Automated Picking of Cryo-EM Particle Images of Biological Macromolecules. Bioinformatics, 36, 1252-1259.
https://doi.org/10.1093/bioinformatics/btz728 |
| [14] | Tegunov, D. and Cramer, P. (2019) Real-Time Cryo-Electron Microscopy Data Preprocessing with Warp. Nature Methods, 16, 1146-1152. https://doi.org/10.1038/s41592-019-0580-y |
| [15] | Wang, F., Gong, H., Liu, G., Li, M., Yan, C., Xia, T., Li, X. and Zeng, J. (2016) DeepPicker: A Deep Learning Approach for Fully Automated Particle Picking in Cryo-EM. Journal of Structural Biology, 195, 325-336.
https://doi.org/10.1016/j.jsb.2016.07.006 |
| [16] | Sigworth, F.J. (2016) Principles of Cryo-EM Single-Particle Image Processing. Microscopy, 65, 57-67.
https://doi.org/10.1093/jmicro/dfv370 |
| [17] | Pantelic, R.S., Ericksson, G., Hamilton, N. and Hankamer, B. (2007) Bilateral Edge Filter: Photometrically Weighted, Discontinuity Based Edge Detection. Journal of Structural Biology, 160, 93-102.
https://doi.org/10.1016/j.jsb.2007.07.005 |
| [18] | Zhang, M. and Gunturk, B.K. (2008) Multiresolution Bilateral Filtering for Image Denoising. IEEE Transactions on Image Processing, 17, 2324-2333. https://doi.org/10.1109/TIP.2008.2006658 |
| [19] | Wang, Y., Chen, Q. and Zhang, B. (1999) Image Enhancement Based on Equal Area Dualistic Sub-Image Histogram Equalization Method. IEEE Transactions on Consumer Electronics, 45, 68-75. https://doi.org/10.1109/30.754419 |
| [20] | Sutskever, I., Hinton, G.E. and Taylor, G.W. (2008) The Recurrent Temporal Restricted Boltzmann Machine. Proceedings of the Twenty-Second Annual Conference on Neural Information Processing Systems, Vancouver, 8-11 December 2008, 1601-1608. |
| [21] | Larochelle, H., Mandel, M., Pascanu, R. and Bengio, Y. (2012) Learning Algorithms for the Classification Restricted Boltzmann Machine. The Journal of Machine Learning Research, 13, 643-669. |
| [22] | Hinton, G.E. (2012) A Practical Guide to Training Restricted Boltzmann Machines. In: Neural Networks: Tricks of the Trade, Springer, Berlin, 599-619. https://doi.org/10.1007/978-3-642-35289-8_32 |
| [23] | Salakhutdinov, R., Mnih, A. and Hinton, G. (2007) Restricted Boltzmann Machines for Collaborative Filtering. Proceedings of the 24th International Conference on Machine Learning, Corvallis, 20-24 June 2007, 791-798.
https://doi.org/10.1145/1273496.1273596 |
| [24] | Punjani, A., Rubinstein, J.L., Fleet, D.J. and Brubaker, M. (2017) cryoSPARC: Algorithms for Rapid Unsupervised Cryo-EM Structure Determination. Nature Methods, 14, 290-296. https://doi.org/10.1038/nmeth.4169 |
